jtydhr88 / sd-webui-3d-editor Goto Github PK

A custom extension for sd-webui that with 3D modeling features (add/edit basic elements, load your custom model, modify scene and so on), then send screenshot to txt2img or img2img as your ControlNet's reference image, basing on ThreeJS editor

JavaScript 98.26% HTML 0.55% Python 0.09% CSS 1.10%

sd-webui-3d-editor's Introduction

Stable Diffusion WebUI 3D Editor

A custom extension for AUTOMATIC1111/stable-diffusion-webui that with 3D modeling features (add/edit basic elements, load your custom model, modify scene and so on), then send screenshot to txt2img or img2img as your ControlNet's reference image, basing on ThreeJS editor

About ThreeJS and ThreeJS Editor

Please refer to ThreeJS and ThreeJS Editor for more information.

Features

load your custom models
export model
add/edit basic elements
edit scene
send screenshot to ControlNet as reference image
more features

Installation

Just like you install other extension of webui:

go to Extensions -> Install from URL
paste this repo link
install
go to Installed, apply and restart UI

How to build

download NodeJs, and install
run npm install
run webpack --mode production

Known Issues

currently, you need to manual resize browser at the first time to show up the canvas (I will try to figure out the solution soon)

Credits

Created by jtydhr88 and basing on ThreeJS editor

My other extension for Stable diffusion webui

3D Model/pose loader A custom extension for AUTOMATIC1111/stable-diffusion-webui that allows you to load your local 3D model/animation inside webui, or edit pose as well, then send screenshot to txt2img or img2img as your ControlNet's reference image.
Canvas Editor A custom extension for AUTOMATIC1111/stable-diffusion-webui that integrated a full capability canvas editor which you can use layer, text, image, elements and so on, then send to ControlNet, basing on Polotno.
StableStudio Adapter A custom extension for AUTOMATIC1111/stable-diffusion-webui to extend rest APIs to do some local operations, using in StableStudio.
Txt/Img to 3D Model A custom extension for sd-webui that allow you to generate 3D model from txt or image, basing on OpenAI Shap-E.

sd-webui-3d-editor's People

Contributors

Stargazers

Watchers

Forkers

cyhunter syndicatefilms ehtick daddongoba chen-shixin mosta1999 cdosrunwild progray steveefemsc xiaox1311 papiguy jasonlau222

sd-webui-3d-editor's Issues

UI Theme Becoming Dull

The extension appears to be changing the overall UI Theme to somewhat duller.
AUTOMATIC1111 stable-diffusion-webui v1.4.0

Win 11
Mozilla Firefox
Microsoft Edge
Google Chrome

Before: Disregard the other Extensions, The UI Theme issue remained prevalent.

After:

texture generation

It is good to have a feature to generate textures inside sd webui for the 3d assets.
https://www.meshy.ai/ provides this feature.

Hi , 3d to 3d , 3d model to 3d model with texture and uv

Hi i just went to download your model it really pain in my ass to download it full from stable diffusion i wish i could download files separately too . i love if you make a addon for your plugin for blender to stable diffusion and also i want to import models to make textures on them or just fix them in it or edit the models that could be cool . like i select a part and then edit it in blender and stable diffusion with prompt and also be able to add several image in it like for forward and sides and back to make image better or even when it make a 3d model i be able to have the images separately for edit the model better . there can be a lot of different thing that can help , like make a help from a character creator and remake the models base of humans and at same time keeping the humanoid rigs for it . editing animations and else but im not sure how much year i have to wait for them lol

Expose the API

since I also made extension https://github.com/jtydhr88/sd-webui-txt-img-to-3d-model, in order to fix jtydhr88/sd-webui-txt-img-to-3d-model#11, this one, 3d editor, should expose the api of import model.

显示不出来

Send to ControlNet needs to be more friendly

currently, Send to ControlNet only support:

send full canvas
only send to the first ControlNet tab

it needs to be more friendly.